remote sensing

Article
Comparison of Machine Learning Methods for Predicting Soil
Total Nitrogen Content Using Landsat-8, Sentinel-1, and
Sentinel-2 Images
Qingwen Zhang 1,† , Mingyue Liu 1,2,3,4,† , Yongbin Zhang 1,† , Dehua Mao 5 , Fuping Li 1,2,3,4 , Fenghua Wu 1 ,
Jingru Song 1 , Xiang Li 1 , Caiyao Kou 1 , Chunjing Li 6 and Weidong Man 1,2,3,4, *

1 College of Mining Engineering, North China University of Science and Technology, Tangshan 063210, China;
[email protected] (Q.Z.); [email protected] (M.L.); [email protected] (Y.Z.);
[email protected] (F.L.); [email protected] (F.W.); [email protected] (J.S.);
[email protected] (X.L.); [email protected] (C.K.)
2 Tangshan Key Laboratory of Resources and Environmental Remote Sensing, Tangshan 063210, China
3 Hebei Industrial Technology Institute of Mine Ecological Remediation, Tangshan 063210, China
4 Collaborative Innovation Center, Green Development and Ecological Restoration of Mineral Resources,
Tangshan 063210, China
5 Key Laboratory of Wetland Ecology and Environment, Northeast Institute of Geography and Agroecology,
Chinese Academy of Sciences, Changchun 130102, China; [email protected]
6 College of Geography and Ocean Sciences, Yanbian University, Yanji 133000, China; [email protected]
* Correspondence: [email protected]; Tel.: +86-315-880-5408
† These authors contributed equally to this work.

Abstract: Soil total nitrogen (STN) is a crucial component of the ecosystem’s nitrogen pool, and
accurate prediction of STN content is essential for understanding global nitrogen cycling processes.
This study utilized the measured STN content of 126 sample points and 40 extracted remote sensing
variables to predict the STN content and map its spatial distribution in the northeastern coastal region
of Hebei Province, China, employing the random forest (RF), gradient boosting machine (GBM), and
Citation: Zhang, Q.; Liu, M.; Zhang, extreme gradient boosting (XGBoost) methods. The purpose was to compare the ability of remote
Y.; Mao, D.; Li, F.; Wu, F.; Song, J.; Li, sensing images (Landsat-8, Sentinel-1, and Sentinel-2) with different machine learning methods for
X.; Kou, C.; Li, C.; et al. Comparison predicting STN content. The research results show the following: (1) The three machine learning
of Machine Learning Methods for methods accurately predicted the STN content and the optimal model provided by the XGBoost
Predicting Soil Total Nitrogen method, with an R2 of 0.627, RMSE of 0.127 g·kg−1 , and MAE of 0.092 g·kg−1 . (2) The combination
Content Using Landsat-8, Sentinel-1,
of optical and synthetic aperture radar (SAR) images improved prediction accuracy, with the R2
and Sentinel-2 Images. Remote Sens.
improving by 45.5%. (3) The importance of optical images is higher than that of SAR images in the
2023, 15, 2907. https://doi.org/
RF, GBM, and XGBoost methods, with optical images accounting for 87%, 76%, and 77% importance,
10.3390/rs15112907
respectively. (4) The spatial distribution of STN content predicted by the three methods is similar.
Academic Editors: Tiziana Simoniello Higher STN contents are distributed in the northern part of the study area, while lower STN contents
and Gabriel Brito Costa are distributed in coastal areas. The results of this study can be very useful for inventories of soil
Received: 26 April 2023 nitrogen and provide data support and method references for revealing nitrogen cycling.
Revised: 31 May 2023
Accepted: 1 June 2023 Keywords: soil total nitrogen content; random forest; gradient boosting machine; extreme gradient
Published: 2 June 2023 boosting; remote sensing; digital soil mapping

Copyright: © 2023 by the authors. 1. Introduction

Licensee MDPI, Basel, Switzerland.
Nitrogen is one of the key essential nutrients for plant growth and development [1].
This article is an open access article
distributed under the terms and
Low levels of nitrogen can negatively impact plant growth, while excessive nitrogen levels
conditions of the Creative Commons
can lead to reduced ecosystem productivity and environmental pollution [2,3]. Soil is a
Attribution (CC BY) license (https:// crucial nitrogen pool in terrestrial ecosystems, playing a fundamental role in the global
creativecommons.org/licenses/by/ nitrogen cycle [4]. However, the rapid development of the economy has caused changes
4.0/). in land use types, particularly the conversion of natural ecosystems to artificial ones [5,6],

Remote Sens. 2023, 15, 2907. https://doi.org/10.3390/rs15112907 https://www.mdpi.com/journal/remotesensing

Remote Sens. 2023, 15, 2907 2 of 22

which are significantly affecting the physical and chemical properties of soil, including
nitrogen [7]. Therefore, a comprehensive understanding of the distribution of soil total
nitrogen (STN) content is essential for sustainable land-use management and provides the
basis for soil nutrient measurements.
STN content is influenced by several factors, including parent soil material, land
use type, and surface vegetation cover, and is unevenly distributed throughout the soil.
The traditional measurement of STN content is based on the laboratory analysis of field
soil sampling, which is time-consuming and labor-intensive, meaning it is challenging to
predict the distribution of STN content over large areas [8]. Digital soil mapping (DSM)
is a method of predicting soil properties and categories across large areas from discrete
samples, which can reduce the cost and labor associated with sampling and analysis [9].
DSM techniques establish a quantitative relationship between soil observations in the field
and readily available variables, which enables the prediction of soil properties across large
areas [10].
Remote sensing data provide effective monitoring for large areas with poor acces-
sibility and produce consistent and comprehensive data over a wide range of time and
space [11]. Based on these advantages, remote sensing data are widely used to estimate
the physicochemical properties of soil. Optical imagery is the most used type of remote
sensing data. The Landsat series of images has made significant contributions to DSM with
its free access and long-time series [12]. However, due to its long return cycle and cloud
cover limitations, data availability within certain time frames can be limited. When com-
pared to the Landsat series, the Sentinel-2 images are also easily accessible; it has a shorter
return cycle, higher spatial resolution, and can more accurately reflect the soil-vegetation
relationship with its red edge bands. As a result, it has gained significant attention in
recent years [13]. Zhou et al. used the band reflectance of multispectral images (Landsat-8,
Sentinel-2, and Sentinel-3 images) to predict the soil organic carbon content [14]. Some
scholars also use remote sensing indices to predict soil properties; Xu et al. used the remote
sensing indices calculated by Landsat-8, Sentinel-2, and WorldView-2 images to predict
STN content [15]. In addition, synthetic aperture radar (SAR) images are increasingly being
used for DSM due to their unique advantages: (1) independence from cloud and fog cover,
as well as day/night cycles, allowing for 24-h imaging; (2) the capability of penetrating
vegetation; (3) data complexity and diversity, offering broad application prospects. The re-
cently launched SAR satellites, such as Sentinel-1 and Gaofen-3, have attracted researchers
to explore their potential in predicting soil properties. Among them, Sentinel-1 data have
shown promising application potential in soil property mapping [16,17]. Yang et al. found
that the backscatter coefficients of multi-temporal Sentinel-1 images were useful indicators
with which to characterize the spatial variability of soil properties in the coastal wetlands
of eastern China [18].
Although remote sensing images have been widely used to predict soil properties,
most studies have incorporated additional cofactors, such as terrain and climate, to accu-
rately predict soil properties in areas with larger variations in these factors [14]. However,
in areas with less topographic and climatic changes, such as plains and coastal areas,
the spatial distribution of STN content cannot be effectively reflected due to the limited
spatial heterogeneity of topographic and climatic factors [1]. High-resolution remote sens-
ing imagery has unique advantages in reflecting ground feature information, providing
promising opportunities for predicting soil properties in areas with small variations in
environmental factors.
Some statistical techniques for predicting STN content have been developed. Statistical
methods, such as multiple linear regression [19], partial least square regression [20], linear
mixed regression [21], and regression kriging [22], are widely used to predict the spatial
prediction of soil properties. However, these methods can only reflect linear relationships,
and most of the relationships between soil properties and various factors are nonlinear, so
there is great uncertainty. Recently, machine learning algorithms, including random forest
(RF) [23], support vector machine [24], boosted regression tree (BRT) [25], extreme gradient
Remote Sens. 2023, 15, 2907 3 of 22

boosting (XGBoost) [26], and generalized boosted machines (GBM) [27], have emerged to
help explain nonlinear relationships. However, choosing the best modeling method for a
given region has always been a challenge for soil property mapping [28].
The primary objective of this study was to map the STN content in the coastal wetlands
of northeast Hebei, China, using Landsat-8, Sentinel-1, and Sentinel-2 images, and to
evaluate the effectiveness of different remote sensing sensors. Landsat-8, Sentinel-1, and
Sentinel-2 images were obtained for generating predictors (multispectral remote sensing
bands, remote sensing indices, and backscatter coefficients). We utilized RF, GBM, and
XGBoost methods to compare the prediction accuracy of different combinations of these
predictor variables in predicting STN content. Furthermore, we assessed the potential of
different remote sensing sensors, such as Landsat-8, Sentinel-1, Sentinel-2, and different
combinations of sensors, for mapping STN content. We then investigated the importance
of the generated predictor variables. Finally, we plotted the spatial distribution of STN
content in the study area based on the optimal models. This study helps to explore the
most suitable remote sensing imagery and machine learning methods for predicting STN
content in coastal areas. The map of STN content provides a better understanding of land
resources, helps assess land suitability for different uses, and aids in land planning and
decision-making.

2. Materials and Methods

2.1. Study Area
The study area is located in the northeast of Hebei, China (38.92◦ –40.32◦ N,
118.14◦ –119.85◦ E) (Figure 1) and covers an approximate area of 7387 km2 . It is a typical
plateau continental climate, with a mean annual temperature and mean annual precipita-
tion of 12.4 ◦ C and 1086.6 mm, respectively. The region is mainly composed of plains, with
mountains in the north and elevations ranging from 0 to 1091 m, with an average elevation
of 43 m. The eastern and southern parts of the study area are adjacent to the sea, located in
a transitional zone between land and sea. It possesses abundant wetland resources and is
an ecosystem with distinct environmental features. STN content in this area is influenced
by both terrestrial and marine factors. Additionally, this area is an important region within
Remote Sens. 2023, 15, x FOR PEER REVIEW 4 of 23
the Bohai economic circle with rapid economic development. The land use in this region is
complex and changes rapidly, and there is a large uncertainty in STN content.

Figure
Figure1.1.Location
Locationofof
the study
the area
study and
area soilsoil
and samples.
samples.

2.2. Satellite Imagery and Processing

The remote sensing data used for modeling included Landsat‐8, Sentinel‐1, and Sen‐
tinel‐2 images; the specific parameter information is shown in Table 1. Three Landsat‐8
images covering the study area were downloaded from Geospatial Data Cloud
Remote Sens. 2023, 15, 2907 4 of 22

2.2. Satellite Imagery and Processing

The remote sensing data used for modeling included Landsat-8, Sentinel-1, and
Sentinel-2 images; the specific parameter information is shown in Table 1. Three Landsat-8
images covering the study area were downloaded from Geospatial Data Cloud (https:
//www.gscloud.cn/, accessed on 10 November 2022). Radiometric calibration and atmo-
spheric correction were performed on Landsat-8 images. Two Sentinel-1 images (single-look
complex (SLC) products) covering the study area were downloaded from the Google Earth
Engine platform and are in IW (interferometric wide swath) mode. Three Sentinel-2 images
were downloaded from the European space agency (ESA) website (https://www.esa.int/,
accessed on 12 November 2022) as Level-2A products, which were already atmospherically
corrected with the Sen2Cor processor and PlanetDEM digital elevation model. These
images were then mosaiced and clipped to obtain an optical image covering the study area.

Table 1. List of remote sensing images in this study.

Satellite Date Number of Images Pixel Size (m) Width of Cloth (km)
24 October 2020 2
Landsat-8 30 × 30 185
31 October 2020 1
15 September 2020 1
Sentinel-1 10 × 10 250
20 September 2020 1
Sentinel-2 16 September 2020 3 10 × 10 and 20 × 20 290

A total of 40 remote sensing variables were extracted from all the remote sensing
images, including 13 derived from Landsat-8, 22 from Sentinel-2, and 5 from Sentinel-1
(Table 2). Spectral bands 1 to 7 (from 0.43 to 2.29 µm) of Landsat-8 images, 10 spectral
bands from the Sentinel-2 images (B2, B3, B4, B5, B6, B7, B8, B8A, B11, and B12), and
2 polarization modes from the Sentinel-1 images (Vertical-vertical polarization and Vertical-
horizontal polarization) were utilized. In addition, we calculated vegetation indices from
Landsat-8 and Sentinel-2 (normalized difference vegetation index (NDVI), ratio vegetation
index (RVI), and difference vegetation index (DVI)), which were reported to be strongly
correlated with STN content [29]. The bare soil index (BSI) has a negative correlation with
STN content, indicating that a higher degree of land surface bareness corresponds to a
lower STN content. BSI can be used as a remote sensing method to monitor land surface
bareness and can be combined with soil sampling data to analyze the spatial distribution of
STN content [30]. The normalized difference built-up index (NDBI) was selected to reflect
the impact of human buildings on STN content, as there are urban and village areas in the
study area [31]. The normalized difference water index (NDWI) was initially used for water
body monitoring [32], and later studies have used it to predict STN content, which has a
strong positive correlation with STN content [33]. Sentinel-2 images have three red edge
bands between the visible and near-infrared bands, which are more sensitive to monitoring
plant photosynthesis. STN content is closely related to vegetation growth status and type,
and thus the red edge bands can be used to estimate STN content [34]. This study used
three red edge bands to calculate six commonly used red edge indices to predict STN
content. All covariates were resampled to have a similar scale and the same cell size of
30 × 30 m [35,36].
Remote Sens. 2023, 15, 2907 5 of 22

Table 2. List of all remote sensing variables in the study for STN prediction.

Satellite Definition Abbreviation Formula

Coastal band L_B1
Blue band L_B2
Green band L_B3
Red band L_B4
Near-infrared band L_B5
Shortwave infrared-1 band L_B6
Landsat-8 Shortwave infrared-2 band L_B7
Normalized difference vegetation index L_NDVI (L_B5 − L_B4)/L_B5 + L_B4)
Ratio vegetation index L_RVI L_B5/L_B4
Difference vegetation index L_DVI L_B5 − L_B4
Bare soil index L_BSI ( L B4+ L B6)−( L B5+ L B2)
1 + ( L− B4+ L− B6)+( L− B5+ L− B2)
− − − −
Normalized difference built-up index L_NDBI ( L_B6 − L_B5)/( L_B6 + L_B5)
Normalized difference water index L_NDWI ( L_B3 − L_B5)/( L_B3 + L_B5)
VV-polarization of the backscatter coefficients VV
VH-polarization of the backscatter coefficients VH
Sentinel 1 Polarization combination 1 VV+VH
Polarization combination 2 VV-VH
Polarization combination 3 VV/VH
Blue band S_B2
Green band S_B3
Red band S_B4
Vegetation red edge-1 S_B5
Vegetation red edge-2 S_B6
Vegetation red edge-3 S_B7
Near-infrared band S_B8
Narrow near-infrared band S_B8A
Shortwave infrared-1 band S_B11
Shortwave infrared-2 band S_B12
Normalized difference vegetation index S_NDVI (S_B8 − S_B4)/(S_B8 + S_B4)
Sentinel-2
Ratio vegetation index S_RVI S_B8/S_B4
Difference vegetation index S_DVI S_B8 − S_B4
Bare soil index S_BSI (S_B4+S_B11)−(S_B8+S_B2)
1 + (S_B4+S_B11)+(S_B8+S_B2)
Normalized difference built-up index S_NDBI (S_B11 − S_B8)/(S_B11 + S_B8)
Normalized difference water index S_NDWI (S_B3 − S_B8)/(S_B3 + S_B8)
Chlorophyll index of Red-edge S_CIRE (S_B7 − S_B5) − 1
Normalized difference Red-edge 1 S_NDRE1 (S_B6 − S_B5)/(S_B6 + S_B5)
Normalized difference Red-edge 2 S_NDRE2 (S_B7 − S_B5)/(S_B7 + S_B5)
Normalized difference vegetation index red-edge 1 S_NDVIRE1 (S_B8 − S_B5)/(S_B8 + S_B5)
Normalized difference vegetation index red-edge 2 S_NDVIRE2 (S_B8-S_B6)/(S_B8+S_B6)
Normalized difference vegetation index red-edge 3 S_NDVIRE3 (S_B8-S_B7)/(S_B8+S_B7)

2.3. Soil Sampling and Analysis

A total of 126 soil samples (0–30 cm) were randomly collected within the study area in
2020 (Figure 1), with a straight-line interval of sampling points for approximately 5 km.
The geographic coordinates, vegetation types, land uses, and soil types were duly recorded
at each sampling site. Three soil samples were collected and thoroughly mixed at each
sampling point to form a composite sample for determining the STN content at that
sampling point. All soil samples were air-dried for three weeks, subsequently crushed, and
sifted through a 2 mm sieve. STN content was measured using the Kjeldahl method [37].
A descriptive statistical analysis of the target STN content was performed. The statisti-
cal properties of the measured STN content at the sampling sites are presented in Table 3.
The measured STN content is defined as moderately variable (with a coefficient of variation
(CV) value of 59.86%), ranging from 0.052 to 2.396 g·kg−1 , with an average of 0.745 g·kg−1 .
The standard deviation (SD) of the STN content was 0.446 g·kg−1 .
 Remote Sens. 2023, 15, 2907 6 of 22

Table 3. Summary statistics of measured STN content at sample locations.

Minimum Maximum Mean Median SD

CV %
(g·kg−1 ) (g·kg−1 ) (g·kg−1 ) (g·kg−1 ) (g·kg−1 )
STN 0.052 2.396 0.745 0.764 0.446 59.866

2.4. Predictive Models

The RF, GBM, and XGBoost methods are currently the most commonly used tree-
based machine learning methods. Models based on these three methods were implemented
through the “train” function in the “caret” package in R-4.2.3-software, and the model
parameters were optimized using the grid search method. The final modeling used the
parameter combination that resulted in the minimum prediction error.

2.4.1. Random Forest

RF is a commonly used machine learning algorithm. It is a model composed of a
random collection of independently trained decision trees [38]. The training data for each
decision tree is obtained by random sampling with replacement from the original dataset,
and the final model’s prediction is the average of all decision tree results (Figure 2). The
advantages of the RF method have the ability to (1) handle nonlinear relationships between
multiple predictors, (2) identify and correct overfitting problems, thereby improving predic-
tion accuracy, (3) handle high-dimensional data and automatically deal with missing and
Remote Sens. 2023, 15, x FOR PEER REVIEW 7
outlier values, and (4) output the importance of each predictor to the model’s prediction,
which further helps understand the influencing factors of the soil properties [39].

Figure
Figure 2. 2. Schematic
Schematic diagram
diagram of random
of random forest method.
forest method.

2.4.2. Gradient Boosting Machine

2.4.2. Gradient Boosting Machine
The GBM method is also comprises decision trees similar to RF. However, the GBM
methodThe
is a GBM method
weighted is method
iterative also comprises decision
for generating trees
decision similar
trees, to RF.
so the trees However,
in the GBM the
model
methodcan be
is anon-independent
weighted iterative[40]. The GBM method
method first generates
for generating a decision
decision treeso
trees, using
the trees i
the
GBMoriginal
model dataset, then
can be calculates the prediction
non‐independent error,
[40]. The GBMandmethod
adjusts the sample
first weights
generates a decision
based on the prediction error. When generating the next round of decision trees, the GBM
using the original dataset, then calculates the prediction error, and adjusts the sa
weights based on the prediction error. When generating the next round of decision
the GBM method prioritizes the sampling of samples with larger prediction errors t
hance the model’s ability to fit these difficult‐to‐predict samples. The steps are as fo
[41]:
Remote Sens. 2023, 15, 2907 7 of 22

method prioritizes the sampling of samples with larger prediction errors to enhance the
model’s ability to fit these difficult-to-predict samples. The steps are as follows [41]:
Step 1: Initialize the model with a constant value:
n
F0 ( x ) = argmin ∑i=1 l (yi , γ), (1)
γ

where F0 ( x ) is the function initially assumed by GBM, γ is an initial constant, n is the total
number of samples, i is the index of the sample, and l (y, F ( x )) is the loss function.
Step 2: Looping: m = 1 to M (where m represents the iteration number and M is the
predetermined number of iterations, i.e., the number of trees).
a. Compute residuals:

∂l (yi , F ( xi ))
rim = − . . . . . . for i = 1, . . . , n, (2)
∂F ( xi )
where rim represents the residual of the i sample in the m iteration.
b. Fit a decision tree hm ( x ) to the residuals.
c. Compute multiplier γm :

n
γm = argmin ∑i=1 l (yi , Fm−1 ( xi ) + γhm ( xi )), (3)
γ

d. Update the model:

Fm ( x ) = Fm−1 ( x ) + γm hm ( x ), (4)
Repeat Step 2 iteratively for M times and output FM ( x ).
The GBM method calculates the contribution of each feature to the loss function and
then weighs the features according to their contribution. This can increase the model’s
attention to important features, reduce attention to unimportant features, and improve the
accuracy and generalization ability of the models.

2.4.3. Extreme Gradient Boosting

The XGBoost method is an optimization of the GBM method, which introduces regu-
larization to prevent overfitting and improve model generalization performance on top of
the original GBM method [42]. The regularization term is added to the loss function, and
the new loss function becomes
n M
Loss(y, F ( x )) = ∑i l (y, F ( x )) + ∑m Ω( f m ), (5)

where Ω( f m ) is the regularization term for the m iteration.

It also incorporates a novel algorithm for splitting nodes that can speed up training
and improve model accuracy [43].

2.5. Recursive Feature Elimination

Some of the remote sensing variables may not provide useful information for predict-
ing the target STN content, as they may be redundant or highly correlated. It is necessary to
select the subset of features that can best represent the characteristics of the soil to improve
the prediction accuracy of the models and to reduce computation and data storage costs.
Recursive feature elimination (RFE) is a commonly used feature selection method that can
be used to determine which remote sensing variables are most important in building STN
content prediction models [44]. In this study, we used the “rfFuncs” method to sort the
model as an argument, making 40 iterations the preset number of features, which decreased
from 40 to 1. RFE removed the least important feature and retrained the model using
the remaining features at each iteration. The trained model was then used to predict the
 Remote Sens. 2023, 15, 2907 8 of 22

validation set, and the root mean square error (RMSE) was calculated. The number of
features corresponding to the smallest RMSE was selected, and the feature variables were
outputted. RFE is performed using the “rfe” function of the R software.

2.6. Model Validation

We constructed STN content models using three different machine learning methods
and various combinations of predictor variables. The combinations of the different factors
are shown in Table 4. Model I, Model II, and Model III used Landsat-8-, Sentinel-1-, and
Sentinel-2-derived predictors, respectively, to predict STN content. Model IV and Model V
were combinations of Landsat-8-derived predictors with Sentinel-1- and Sentinel-2- derived
predictors, respectively, and Model VI used a combination of Sentinel-1- and Sentinel-2-
derived predictors. Model VII included all predictor variables. Figure 3 shows an overview
of the flowchart for STN content mapping using these experimental models. For the
predictive performance of these models, we used a 10-fold cross-validation method [45]. For
the 10-fold cross-validation, we randomly divided the observed dataset into 10 groups [46].
In each of the 10 folds, one group was designated as the test dataset and the other nine
groups were used as the training set [47]. Three validation criteria were calculated to
Remote Sens. 2023, 15, x FOR PEER REVIEW
evaluate the performance of the model: the RMSE, the mean absolute error (MAE), 9and of 23
2
the coefficient of determination (R ). These validation criteria are calculated from the
following [25]:
2
∑n (ŷ − y)
R2 = in=1 l 2
(6)
∑i=11(yi − y)
𝑅𝑀𝑆𝐸 s 𝑦 𝑦 (7)
1𝑛 n
n i∑
RMSE = (ŷi − yi )2 (7)
=1

11 n
n𝑛i∑
𝑀𝐴𝐸=
MAE l − yi𝑦| |
|ŷ|𝑦 (8)(8)
=1
where 𝑛n represents
where representsthe thenumber
number of of
samples, ŷl and
samples, yi represent
𝑦 and the predicted
𝑦 represent and observed
the predicted and ob‐
values at site i, respectively, and y represent the mean of observed values.
served values at site 𝑖, respectively, and 𝑦 represent the mean of observed values.

Figure 3. Overview of the flowchart for STN content prediction.

Figure 3. Overview of the flowchart for STN content prediction.

Table 4. Different combinations of variables used as inputs for STN content prediction.

No. Model Variables

1 Model I Landsat‐8 predictors
2 Model II Sentinel‐1 predictors
3 Model III Sentinel‐2 predictors
4 Model Ⅳ Landsat‐8 + Sentinel‐1 predictors
Remote Sens. 2023, 15, 2907 9 of 22

Table 4. Different combinations of variables used as inputs for STN content prediction.

No. Model Variables

1 Model I Landsat-8 predictors
2 Model II Sentinel-1 predictors
3 Model III Sentinel-2 predictors
4 Model IV Landsat-8 + Sentinel-1 predictors
5 Model V Landsat-8 + Sentinel-2 predictors
6 Model VI Sentinel-1 + Sentinel-2 predictors
7 Model VII Landsat-8 + Sentinel-1 + Sentinel-2 predictors

3. Results
3.1. Model Evaluation and Comparison
The performances of the RF, GBM, and XGBoost methods based on different com-
binations of predicting STN content are shown in Table 5. The different methods and
variable combinations significantly affected the modeling performance. For the RF and
GBM methods, Model I (R2 = 0.446 vs. R2 = 0.410, respectively), Model II (R2 = 0.411 vs.
R2 = 0.391, respectively), and Model III (R2 = 0.409 vs. R2 = 0.394, respectively) were better
predicted by the RF, indicating that the RF method is better than GBM in predicting STN
content using single-type remote sensing data. However, the GBM method performed
better than RF in Model IV (R2 = 0.479 vs. R2 = 0.459, respectively), Model V (R2 = 0.496 vs.
R2 = 0.463, respectively), Model VI (R2 = 0.488 vs. R2 = 0.457, respectively), and Model VII
(R2 = 0.533 vs. R2 = 0.475, respectively), indicating that the GBM method is more suitable
than RF for predicting STN content using multiple source remote sensing data. Among the
three machine learning methods, whether using single or multiple data types as prediction
variables, the XGBoost method has the highest prediction accuracy for STN content.

Table 5. Performance results of RF, GBM, and XGBoost in predicting STN content based on different
combinations of variables. The most accurate results are shown in bold.

Modeling Technique Model RMSE (g·kg−1 ) MAE (g·kg−1 ) R2

I 0.193 0.134 0.446
II 0.216 0.158 0.411
III 0.194 0.140 0.409
RF IV 0.183 0.127 0.459
V 0.181 0.125 0.463
VI 0.179 0.130 0.457
VII 0.175 0.123 0.475
I 0.247 0.176 0.410
II 0.277 0.208 0.391
III 0.239 0.177 0.394
GBM IV 0.210 0.154 0.479
V 0.201 0.140 0.496
VI 0.205 0.146 0.488
VII 0.184 0.130 0.533
I 0.176 0.131 0.498
II 0.226 0.171 0.431
III 0.167 0.125 0.524
XGBoost IV 0.160 0.121 0.545
V 0.138 0.101 0.593
VI 0.150 0.107 0.564
VII 0.127 0.092 0.627

When comparing different combinations of predictive variables, Model I (R2 = 0.446

and R2 = 0.410 for RF and GBM methods, respectively) performed better than Model II
(R2 = 0.411 and R2 = 0.391 for the RF and GBM methods, respectively) and Model III
(R2 = 0.409 and R2 = 0.394 for the RF and GBM methods, respectively), indicating that
Landsat-8 images have a better predictive capability than the Sentinel-1 and Sentinel-2
images when modeling using the RF and GBM methods; Model II and Model III have
similar prediction levels, indicating that Sentinel-1 and Sentinel-2 images have similar
predictive capabilities. For the models that were established using the XGBoost method, the
R2 of Model I and Model III is 15.5% (from 0.431 to 0.498) and 21.6% (from 0.431 to 0.524)
higher than that of Model II, respectively, indicating that optical imagery performs better
Remote Sens. 2023, 15, 2907 10 of 22

than SAR imagery. When compared with single-type remote sensing data, the combination
of different types of data can improve prediction accuracy, and the addition of each type
of data has a different degree of improvement in model accuracy. For example, when
Sentinel-1 and Sentinel-2 predictors were added to Model I to form Model IV and Model V,
the highest R2 increased by 16.83% and 20.98%, respectively. When Sentinel-2 predictors
were added to Model II to form Model VI, the highest R2 increased by 37.5%. This indicates
that the added data contain valuable information that is different from the original data.
This improvement is similar across all three machine learning methods.
The models built using all prediction factors have the highest prediction accuracy.
Model VII, which combines three types of remote sensing data as prediction factors, showed
Remote Sens. 2023, 15, x FOR PEER REVIEW
the most significant improvement. For example, when compared to Model II 11 andof 23
con-
structed from a single data source, Model VII, based on the XGBoost method, improved the
R2 value from 0.431 to 0.627, an increase of 45.48% compared to Model IV, which combines
two types 2 value of Model VII (0.627) is 15.05% higher than that of Model
of data. The R0.176
I 0.131 0.498
IV (0.545). Model VII is based on three methods (R 2 = 0.475, R2 = 0.533, and R2 = 0.627 for
II 0.226 0.171 0.431
the RF,
III GBM, and XGBoost methods, respectively),
0.167 which can explain the
0.125 variation in STN
0.524
content
Ⅳ
of 47.5%, 53.3%, and 62.7%, respectively. From the distribution of the measured
XGBoost 0.160 0.121 0.545
value and the predicted value scatterplot (Figure 4), the STN content predicted by the
Ⅴ 0.138 0.101 0.593
XGBoost method is closer to the measured value, and the fitted straight line between the
Ⅵ 0.150 0.107 0.564
measured value and the predicted value is closer to the 1:1 line, followed by GBM, and RF
Ⅶ 0.127 0.092 0.627
is the worst.

Scatterplot
Figure4.4.Scatter
Figure plotofofpredicted
predictedSTN
STNcontent
contentvalues
valuesand
and the
the measured
measured STN
STN content
content values
values using
using
RF,
RF, GBM,
GBM, and
andXGBoost.
XGBoost.

3.2.
3.2.Relative
RelativeImportance
ImportanceofofVariables
Variables
Model
Model VII was built basedon
VII was built based onthree
threemachine
machinelearning
learningmethods
methods using
usinga combination
a combination
of all predictive variables. The predictive variables sorted by
of all predictive variables. The predictive variables sorted by relative importance relative importance areare
shown in Figure 5 (percentages were used to enhance comparability).
shown in Figure 5 (percentages were used to enhance comparability). Variables with Variables with less
than 1% importance
less than 1% importance are notaredisplayed in the graph,
not displayed in the as they may
graph, as theybe due
maytobechance.
due toVaria‐
chance.
bles are ranked roughly the same in importance. For example,
Variables are ranked roughly the same in importance. For example, six out of six out of the topthe
nine
topim‐
nine
portant
importantvariables were
variables duplicated
were duplicated in the GBM
in the GBM and XGBoost
and XGBoost methods,
methods,namely
namely VV,VV,L_B5,
L_B5,
S_NDVIRE2,
S_NDVIRE2,VH, VH,S_NDVIRE3,
S_NDVIRE3, andand S_B5. FiveFive
S_B5. duplicated
duplicatedvariables werewere
variables foundfound
in theinRFthe
and XGBoost methods, namely L_NDWI, S_NDVIRE2, L_B5,
RF and XGBoost methods, namely L_NDWI, S_NDVIRE2, L_B5, VH, and VV. L_NDWI VH, and VV. L_NDWI were
the most significant explanatory variables in both models, accounting
were the most significant explanatory variables in both models, accounting for 14.24% for 14.24% and
21.44% of the relative importance in predicting STN content. Four
and 21.44% of the relative importance in predicting STN content. Four variables were variables were dupli‐
cated among
duplicated the top
among thenine mostmost
top nine important
importantvariables in all
variables in three methods,
all three methods, namely,
namely, VV,VV,
L_B5, S_NDVIRE2,
L_B5, S_NDVIRE2, and VH. and VH.
Model
ModelVII, VII,which
whichwas wasconstructed
constructed using the the
using RF method,
RF method, showed that Landsat‐8
showed im‐
that Landsat-8
agery
imagery(relative importance
(relative importance of 63%)
of 63%) is the main
is the explanatory
main explanatory variable forfor
variable STNSTNcontent, fol‐fol-
content,
lowed by Sentinel‐2 (24%) and Sentinel‐1 (13%). Similarly, the XGBoost
lowed by Sentinel-2 (24%) and Sentinel-1 (13%). Similarly, the XGBoost method-established method‐estab‐
lished
ModelModel
VII alsoVII also indicates
indicates that Landsat‐8
that Landsat-8 has thehas the highest
highest relativerelative importance
importance (44%),
(44%), followed
followed by Sentinel‐2 (33%), and Sentinel‐1 has the lowest importance (23%). This sug‐
gests that Landsat‐8 imagery has a stronger explanatory power for STN content than Sen‐
tinel series imagery for both the RF and XGBoost methods. However, GBM method‐es‐
tablished Model VII, Landsat‐8, and Sentinel‐2 have similar explanatory powers. For all
the models established using the RF, GBM, and XGBoost methods, the relative importance
Remote Sens. 2023, 15, 2907 11 of 22

by Sentinel-2 (33%), and Sentinel-1 has the lowest importance (23%). This suggests that
Landsat-8 imagery has a stronger explanatory power for STN content than Sentinel series
imagery for both the RF and XGBoost methods. However, GBM method-established Model
VII, Landsat-8, and Sentinel-2 have similar explanatory powers. For all the models estab-
lished using the RF, GBM, and XGBoost methods, the relative importance of Sentinel-1 is
Remote Sens. 2023, 15, x FOR PEER REVIEW
the lowest, at 13%, 24%, and 23%, respectively. This indicates that optical imagery12is of 23
more
helpful for predicting STN content. The same rules were observed in others, from Model I
to Model VI (Figures A1–A3).

Figure 5. The relative importance of variables used for the STN content prediction in Model Ⅶ
Figure 5. The relative importance of variables used for the STN content prediction in Model VII
based on RF, GBM, and XGBoost methods.
based on RF, GBM, and XGBoost methods.
3.3. Spatial
3.3. Spatial Distribution
Distribution Pattern
Pattern of
of STN
STN Content
Content
Based on the RF, GBM, and XGBoost
Based on the RF, GBM, and XGBoost methods, methods, thethe established
established Model
Model VII VII
waswas se‐
selected
lected to predict the STN content in the entire study area, and a spatial distribution
to predict the STN content in the entire study area, and a spatial distribution map of the map
of the
STN STN content
content in thearea
in the study studywasarea was drawn
drawn (Figure(Figure
6). The6). The spatial
spatial patternspatterns
of STNofcontent
STN
content predicted by the three methods are similar, and a strong spatial
predicted by the three methods are similar, and a strong spatial heterogeneity for STN heterogeneity for
STN content was observed on all of the distribution maps, with higher
content was observed on all of the distribution maps, with higher STN content in the STN content in the
northern part
northern part of
of the
the study
study area
area and
and lower
lower content
contentin incoastal
coastalareas.
areas.Based
Basedononthe
thestatistical
statistical
analysis, the
analysis, thepredicted
predictedSTN STNcontents
contents from
from different
different models
models showshow similarities.
similarities. For in‐
For instance,
in coastal areas, the majority of the pixels have STN contents ranging from 0.4–0.50.4–0.5
stance, in coastal areas, the majority of the pixels have STN contents ranging from g·kg−1 .
g∙kg −1. As we move from coastal wetlands to farmland areas to mountainous areas, the
As we move from coastal wetlands to farmland areas to mountainous areas, the peak of the
peak of the distribution
distribution curve shiftscurve shifts
towards towards
higher STNhigher STNindicating
contents, contents, indicating thatcontent
that the STN the STNin
content in inland areas is significantly higher than
inland areas is significantly higher than that in coastal areas.that in coastal areas.
The three methods predict STN content in the study area, and the descriptive statis‐
tics are shown in Table 6. The SD values for STN content predicted by the RF model are
lower than that predicted by GBM and XGBoost, indicating the robustness of the RF
model is the highest. The predicted average STN content of each model is higher than the
actual value.

Table 6. Descriptive statistics of predicted map of STN content.

Method Minimum (g∙kg−1) Maximum (g∙kg−1) Mean (g∙kg−1) SD (g∙kg−1)

 Remote Sens. 2023, 15, x FOR PEER REVIEW

XGBoost
Remote Sens. 2023, 15, 2907 0.09 2.01 0.80 12 of 22 0.28

Figure
Figure 6. Spatial 6. Spatial
distribution mapdistribution map obtained
of STN content of STN content
based on obtained basedand
the RF, GBM, on the RF, GBM, an
XGBoost
methods
methods (Model (Model +VII:
VII: Landsat-8 Landsat‐8
Sentinel-1 + Sentinel‐1
+ Sentinel-2 + Sentinel‐2 predictors).
predictors).
Remote Sens. 2023, 15, 2907 13 of 22

The three methods predict STN content in the study area, and the descriptive statistics
are shown in Table 6. The SD values for STN content predicted by the RF model are lower
than that predicted by GBM and XGBoost, indicating the robustness of the RF model is the
highest. The predicted average STN content of each model is higher than the actual value.

Table 6. Descriptive statistics of predicted map of STN content.

Minimum Maximum
Method Mean (g·kg−1 ) SD (g·kg−1 )
(g·kg−1 ) (g·kg−1 )
RF 0.17 1.64 0.82 0.22
GBM 0 1.87 0.84 0.26
XGBoost 0.09 2.01 0.80 0.28

4. Discussion
4.1. Accuracy and Influencing Factors of STN Content Prediction Models
The results demonstrate that the prediction methods, different types of data, and dif-
ferent combinations of data significantly influence the STN content predictive accuracy. The
study did not find that the RF method-established models consistently outperformed GBM
in predicting STN content using different variable combinations. Therefore, it is necessary
to calibrate and evaluate competitive prediction models based on specific experimental
datasets under different model combinations. The XGBoost method outperforms the RF
and GBM methods in terms of prediction accuracy, a finding supported by Tien Dat Pham’s
research [27]. However, Zhang et al. used RF, GBM, and XGBoost to study STN content
in tobacco planting areas and found that GBM performed the best, followed by RF, with
XGBoost performing the worst [48]. Some scholars have found that the three methods
perform similarly [49]. This discrepancy may be due to differences in STN sample quantity
as well as the types of remote sensing variables used. There is no consistent conclusion
about the model performance of the RF, GBM, and XGBoost methods. It seems that no
single machine learning method is most suitable for all ecosystems, so it is important to
choose different methods based on different regions and remote sensing variables. As
the RF method calculates an average value of the output values from multiple trees as
the model’s prediction result, it is not sensitive to outliers [50]. This means that the RF
method ignores the effect of extremely high or low STN content values on the prediction of
STN content in the study area, resulting in a small predicted range for STN content in the
entire region. GBM and XGBoost are both iterative models, with each model’s prediction
based on the residuals of the previous model. The models are sensitive to outliers, as a
large outlier may affect the residuals of each model and result in a wider predicted range
of STN content [51]. Based on measured soil data, the STN content ranged from 0.052
to 2.396 g·kg−1 . Among the three machine learning algorithms used in this study, the
XGBoost method was found to be more accurate, supporting the results that XGBoost has
better accuracy.
Our research findings demonstrate the crucial importance of three types of remote
sensing imagery, namely Landsat-8, Sentinel-1, and Sentinel-2, in predicting STN content.
The accuracy of the model based on the derived variables extracted from different remote
sensing images is different. Although both Landsat-8 and Sentinel-2 are optical remote
sensing images, the information contained in the images is different due to differences
in their center wavelength, bandwidth, and overlapping bands [15], and the difference
in image acquisition time also leads to differences in the information contained in the
images [52], which can lead to different prediction capabilities for STN content. The models
(Model II) based on Sentinel-1-derived variables had lower accuracy compared to the
models (Model I and Model III) based on optical image-derived variables. This suggests
that the predictive ability of optical images is superior to SAR images in the study area,
which is consistent with previous research [53]. However, the Sentinel-1 data helped
to improve the accuracy of the models, and the study found that when the predictors
extracted from SAR images were added, the model accuracy improved, indicating that
Remote Sens. 2023, 15, 2907 14 of 22

Sentinel-1 imagery contains useful information beyond Landsat-8 and Sentinel-2 [15]. There
is a study that found the inclusion of Sentinel-1 imagery improves the model accuracy,
contributing 9% and 7% to the RF and BRT models, respectively, supporting the results
of this experiment [53]. The inclusion of different sensor data in the model significantly
improved its accuracy, indicating that Landsat 8, Sentinel-1, and Sentinel-2 images contain
different valuable information. Previous studies on predicting soil properties mainly used a
single sensor, such as Landsat [54] and Sentinel-2 [35,45], without considering the feasibility
of radar sensors. In this study, the better prediction accuracy obtained from the combination
of optical and SAR images demonstrates the usefulness of SAR data in predicting STN
content. The combination of optical and radar sensors has great potential in predicting soil
properties [55].
Among all the prediction models, Model VII, based on the XGBoost method, has the
highest prediction accuracy and can explain 62.7% of the variability in STN content. Our
prediction model has achieved higher accuracy compared to other scholars’ predictions of
STN content. For example, Wadoux et al. established an RF model using French LUCAS
data, which can only explain 20% of the variability in STN content [54]. ZHOU et al. used
data from the Second National Land Survey from 1979 to 1985 to construct XGBoost, RF, and
weighted model averaging methods to predict STN content across China, with R2 values of
0.34, 0.38, and 0.41, respectively [56]. Although public soil datasets have wide coverage and
rich attribute information for the sampling points, they have poor timelines due to their
long sampling time and cannot be matched with recent remote sensing images, thus, they
can only be used to invert soil properties during the sampling period. When compared to
using public datasets, field sampling provides controllable data for specific experiments,
with the spatial and temporal consistency between the samples and remote sensing images
being the most important advantage, which had a certain effect on improving the accuracy
of the model.

4.2. Relative Importance of Variables

In this study, among the RF, GBM, and XGBoost method-established optimal models,
the prediction factors provided by Landsat-8 data accounted for 63%, 37%, and 44% of
the importance of all variables, respectively. The prediction factors provided by Sentinel-2
data accounted for 24%, 39%, and 33% of the importance of all variables, respectively. The
prediction factors provided by Sentinel-1 data accounted for 13%, 24%, and 23% of the
importance of all variables, respectively. It can be seen that optical images are the most
important in explaining the variability of STN content. Among the two optical images,
Landsat-8 has greater importance than Sentinel-2 in all but the GBM prediction results,
where their importance is similar. This suggests that Landsat-8 data have a greater impact
on the study area than Sentinel-2. Additionally, when compared to optical images, SAR
images have lower importance in predicting STN content. This result is supported by the
study of Zhou et al. [53].
The spectral bands, the remote sensing indices of optical imagery, and the backscatter
coefficients of radar imagery are extracted through remote sensing images to help explain
the spatial variation in STN content in the soil-vegetation system. They can capture the
relationship between soil properties and vegetation to reflect soil information to some extent.
Remote sensing images represent a valuable dataset for explaining spatial changes in the soil
in natural vegetation areas [57]. In the RF, GBM, and XGBoost prediction models, remote
sensing indices accounted for 69%, 45%, and 55% of the model’s contribution, respectively.
Remote sensing indices contribute more to the models than band reflectance. Specifically,
in the RF and XGBoost models, remote sensing indices have a higher contribution rate
than band reflectance, indicating that remote sensing indices can better characterize soil
information and have higher values for the prediction of STN content. In addition, band
reflectance is more important than remote sensing indices in GBM models, indicating that
the role of band reflectance is relatively more important in the GBM model. In the RF
and XGBoost models, the importance of NDWI is highest, and soil moisture promotes the
Remote Sens. 2023, 15, 2907 15 of 22

accumulation of ecosystem STN content [58]. Xu’s research also proves that NDWI strongly
correlates with STN content [33]. The sampling sites in this study are mostly located in
intertidal flats, paddy fields, and marsh land cover types, where soil moisture is high,
which is expected to result in the high importance of NDWI. Remote sensing images are
more sensitive to vegetation and are indirectly sensitive to soil properties; the data were
collected from September to October, when vegetation was flourishing, and the calculated
vegetation indices were relatively high. The importance of vegetation indices is high in
this study, among which the red edge index S_NDVIRE2 has a large contribution to the
models. The red edge indices are recognized as the most suitable remote sensing indices
for reflecting vegetation growth [59], which means that they can estimate soil properties
better through the vegetation medium. This view is also supported in this study.

4.3. Spatial Distribution of STN Content

The spatial distribution of STN content predicted in this study is similar to that of
the 0–20 cm STN content data set in China by Zhou et al. [56]. The spatial distribution of
STN content predicted by the three modeling methods is also similar, further indicating
that the results of this study are in line with reality. High levels of STN content were
mainly distributed in the northern mountainous areas that were covered with dense veg-
etation. Correspondingly, low levels of STN content were mainly found in the southern
and central regions that were dominated by high levels of human activity areas such as
coastal and urban areas, indicating that areas with dense tree cover are more conducive to
the accumulation of STN content, which is consistent with the results of Zhou et al. [60].
Cropland STN content is second only to the northern mountainous areas, which may be
due to the fertilization of farmland, which causes some nitrogen elements to infiltrate into
the soil [15,61]. In addition, a large amount of agricultural waste, residue, and feces will
be produced during the agricultural production process, and these materials will degrade
into organic matter and release nitrogen elements, further increasing the STN content [62].
In terms of the prediction results, the spatial distribution of STN based on the XGBoost
method shows that the STN content ranges from 0 to 2.01 g·kg−1 . These distribution
ranges are consistent with those presented in the STN maps produced by Xu et al. [33] and
Li et al. [63].
However, there are some uncertainties in our study. Firstly, time-series images provide
more information compared to single-time remote sensing images, reduce uncertainty
and improve model accuracy, and future studies might consider extracting time-series
remote sensing variables for predicting STN content [18]. This study resampled the spatial
resolution of all the remote sensing variables to 30 m without considering the impact
of spatial resolution on modeling and inversion accuracy. However, different spatial
resolutions can lead to different mixes of land features, thereby affecting the accuracy of
the modeling and inversion. Therefore, it is crucial to determine an appropriate spatial
resolution for predicting soil properties. In the next step of the research, we will pay
attention to considering the impact of spatial resolution on soil property prediction and
explore suitable strategies for selecting spatial resolution to enhance the accuracy and
reliability of the model.

5. Conclusions
This study combined three commonly used remote sensing images, including two
multispectral images (Landsat-8 and Sentinel-2) and one SAR image (Sentinel-1), and used
three decision tree-based machine learning methods (RF, GBM, and XGBoost) to predict
the STN content in a coastal area. The spatial distribution of the STN content was mapped.
Our conclusions are summarized as follows:
Remote Sens. 2023, 15, 2907 16 of 22

• The application of SAR and optical images proved useful for predicting STN content,
and their combination showed enhanced model accuracy. The RF, GBM, and XGBoost
methods demonstrated maximum improvements of 16%, 36%, and 45%, respectively;
• The XGBoost method had higher accuracy than the RF and GBM methods. The optimal
model was built using the XGBoost method, with an R2 of 0.627, RMSE of 0.127 g·kg−1 ,
and an MAE of 0.092 g·kg−1 ;
• Optical imagery is more helpful than SAR imagery in predicting STN content. In
the models established by the RF and XGBoost methods, Landsat-8 had the highest
relative importance (63% and 44%, respectively), followed by Sentinel-2 (24% and
33%, respectively). In the model established by the GBM method, the importance of
Landsat-8 and Sentinel-2 was similar but higher than that of Sentinel-1;
• The STN content predicted by the three models has a certain degree of similarity for
spatial distribution. The predicted range of STN content is from 0 to 2.01 g·kg−1 . These
maps showed significant spatial variability. The STN content is high in the densely
forested areas in the north and low in the paddy wetlands in the southeast.

Author Contributions: Conceptualization, Q.Z., F.W., Y.Z., D.M., M.L. and J.S.; methodology, Q.Z.,
Y.Z., W.M., M.L. and D.M.; software, Q.Z., J.S. and X.L.; validation, W.M., M.L. and F.W.; formal
analysis, W.M. and M.L.; investigation, Q.Z.; resources, C.K. and C.L.; data curation, Q.Z., X.L. and
C.K.; writing—original draft preparation, Q.Z. and W.M.; writing—review and editing, W.M. and
M.L.; visualization, Q.Z., X.L. and C.K.; supervision, Y.Z. and F.L.; project administration, W.M.;
funding acquisition, W.M., M.L. and Y.Z. All authors have read and agreed to the published version
of the manuscript.
Funding: This research was funded by the National Natural Science Foundation of China (Grant
No. 41901375, 42101393, and 52274166), the Natural Science Foundation of Hebei Province, China
(Grant No. D2022209005, D2019209322 and D2019209317), the Funding Project for the Introduction of
Returned Overseas Chinese Scholars of Hebei, China (Grant No. C20200103), Funded by Science and
Technology Project of Hebei Education Department (Grant No. BJ2020058), the Key Research and
Development Program of Science and Technology Plan of Tangshan, China (Grant No. 22150221J), the
North China University of Science and Technology Foundation (Grant No. BS201824 and BS201825),
the Fostering Project for Science and Technology Research and Development Platform of Tangshan,
China (No. 2020TS003b).
Data Availability Statement: The data presented in this study are available on request from the
corresponding author. The data are not publicly available due to privacy restrictions.
Acknowledgments: The authors would like to thank Yufeng Hao, Kuo Zhang, Mimi Gao, Xiaowu
Yang, Hao Zheng, Yahui Liu, Chunyu Li, and Tanglei Song for collecting soil samples. The authors
are deeply grateful to the anonymous reviewers and the editor for their helpful comments on the
manuscript.
Conflicts of Interest: The authors declare no conflict of interest.
 Yang, Hao Zheng, Yahui Liu, Chunyu Li, and Tanglei Song for collecting soil samples. The authors
are deeply grateful to the anonymous reviewers and the editor for their helpful comments on the
manuscript.
Data Availability Statement: The data presented in this study are available on request from the
Remote Sens. 2023, 15, 2907 corresponding author. The data are not publicly available due to privacy restrictions. 17 of 22

Conflicts of Interest: The authors declare no conflict of interest.

Appendix
Appendix A
A

Remote Sens. 2023, 15, x FOR PEER REVIEW 18 of 23

Figure
Figure A1.
A1. Relative
Relative importance
importance of
of variables
variables used
used for
for the
the STN
STN content
content prediction
prediction in
in Model
Model II to
to Model
Model
Ⅵ based on RF method.
VI based on RF method.
Remote Sens. 2023, 15, 2907 18 of 22
Figure A1. Relative importance of variables used for the STN content prediction in Model I to Model
Ⅵ based on RF method.

Remote Sens. 2023, 15, x FOR PEER REVIEW 19 of 23

Figure A2.
Figure A2. Relative
Relative importance
importance of
of variables
variables used
used for
for the
the STN
STN content
content prediction in Model
prediction in Model II to
to Model
Model
Ⅵ based on GBM method.
VI based on GBM method.
Remote Sens. 2023, 15, 2907 19 of 22
Figure A2. Relative importance of variables used for the STN content prediction in Model I to Model
Ⅵ based on GBM method.

Remote Sens. 2023, 15, x FOR PEER REVIEW 20 of 23

Figure A3.
Figure A3. Relative
Relative importance of variables
importance of variables used
used for
for the
the STN
STN content
content prediction
prediction in
in Model
Model II to
to Model
Model
Ⅵ based on XGBoost method.
VI based on XGBoost method.

References
References
1.
1. Wang,
Wang, Y.;
Y.;Zhang,
Zhang,X.; X.;Huang,
Huang,C. C.Spatial
Spatialvariability
variability ofof soil
soil total
total nitrogen
nitrogen and
and soil
soil total
total phosphorus
phosphorus under
under different
different land
land uses
uses in
in aa
small
small watershed
watershed on on the
the Loess
Loess Plateau, China. Geoderma
Plateau, China. 2009, 150,
Geoderma 2009, 150, 141–149.
141–149. [CrossRef]
https://doi.org/10.1016/j.geoderma.2009.01.021.
2.
2. Zhang, Y.;
Y.; Li,
Li, M.;
M.; Zheng,
Zheng, L.;
L.; Qin,
Qin, Q.;
Q.; Lee,
Lee, W.S.
W.S. Spectral
Spectral features
features extraction
extraction for
for estimation
estimation ofof soil
soil total
total nitrogen
nitrogen content
content based
based on
on
modified
modified antant colony
colony optimization algorithm. Geoderma
optimization algorithm. 2019, 333,
Geoderma 2019, 333, 23–34.
23–34. [CrossRef]
https://doi.org/10.1016/j.geoderma.2018.07.004.
3.
3. Sarker,
Sarker, S.;S.;Veremyev,
Veremyev, A.; Boginski, V.; Singh,
A.; Boginski, V.;A.Singh,
CriticalA.Nodes in River
Critical NodesNetworks.
in River Sci. Rep. 2019, 9, 11178.
Networks. [CrossRef]
Sci. Rep. 2019, 9, 11178.
4. Batjes, N.H. Total carbon and nitrogen in the soils of the world. Eur. J. Soil Sci. 1996, 47, 151–163. [CrossRef]
https://doi.org/10.1038/s41598‐019‐47292‐4.
5.
4. Mao,
Batjes,D.; Luo,Total
N.H. L.; Wang,
carbon Z.;and
Wilson, M.C.;
nitrogen inZeng, Y.; Wu,
the soils B.;world.
of the Wu, J. Eur.
Conversions
J. Soil Sci.between
1996, 47,natural wetlands
151–163. and farmland in China:
https://doi.org/10.1111/j.1365‐
A multiscale geospatial
2389.1996.tb01386.x. analysis. Sci. Total Environ. 2018, 634, 550–560. [CrossRef] [PubMed]
6.
5. Gao,
Mao, Y.;
D.;Sarker,
Luo, L.; S.;Wang,
Sarker,Z.;T.;Wilson,
Leta, O.T. Analyzing
M.C.; Zeng, Y.;theWu,
critical locations
B.; Wu, in response
J. Conversions of constructed
between and planned
natural wetlands anddams on the
farmland in
Mekong River Basin for environmental integrity. Environ. Res. Commun. 2022, 4, 101001. [CrossRef]
China: A multiscale geospatial analysis. Sci. Total Environ. 2018, 634, 550–560. https://doi.org/10.1016/j.scitotenv.2018.04.009.
6. Gao, Y.; Sarker, S.; Sarker, T.; Leta, O.T. Analyzing the critical locations in response of constructed and planned dams on the
Mekong River Basin for environmental integrity. Environ. Res. Commun. 2022, 4, 101001. https://doi.org/10.1088/2515‐
7620/ac9459.
7. Yang, L.; Luo, P.; Wen, L.; Li, D. Soil organic carbon accumulation during post‐agricultural succession in a karst area, southwest
China. Sci. Rep. 2016, 6, 37118. https://doi.org/10.1038/srep37118.
8. Yang, R.; Zhang, G.; Yang, F.; Yang, Y.; Yang, D. Comparison of boosted regression tree and random forest models for mapping
Remote Sens. 2023, 15, 2907 20 of 22

7. Yang, L.; Luo, P.; Wen, L.; Li, D. Soil organic carbon accumulation during post-agricultural succession in a karst area, southwest
China. Sci. Rep. 2016, 6, 37118. [CrossRef] [PubMed]
8. Yang, R.; Zhang, G.; Yang, F.; Yang, Y.; Yang, D. Comparison of boosted regression tree and random forest models for mapping
topsoil organic carbon concentration in an alpine ecosystem. Ecol. Indic. 2016, 60, 870–878. [CrossRef]
9. Jeong, G.; Oeverdieck, H.; Park, S.J.; Huwe, B.; Ließ, M. Spatial soil nutrients prediction using three supervised learning methods
for assessment of land potentials in complex terrain. Catena 2017, 154, 73–84. [CrossRef]
10. Minasny, B.; McBratney, A.B. Digital soil mapping: A brief history and some lessons. Geoderma 2016, 264, 301–311. [CrossRef]
11. Forkuor, G.; Hounkpatin, O.K.L.; Welp, G.; Thiel, M. High Resolution Mapping of Soil Properties Using Remote Sensing Variables
in South-Western Burkina Faso: A Comparison of Machine Learning and Multiple Linear Regression Models. PLoS ONE 2017, 12,
e0170478. [CrossRef] [PubMed]
12. Bhattarai, N.; Quackenbush, L.J.; Dougherty, M.; Marzen, L.J. A simple Landsat–MODIS fusion approach for monitoring seasonal
evapotranspiration at 30 m spatial resolution. Int. J. Remote Sens. 2015, 36, 115–143. [CrossRef]
13. Siqueira, R.G.; Moquedace, C.M.; Francelino, M.R.; Schaefer, C.E.G.R.; Fernandes-Filho, E.I. Machine learning applied for
Antarctic soil mapping: Spatial prediction of soil texture for Maritime Antarctica and Northern Antarctic Peninsula. Geoderma
2023, 432, 116405. [CrossRef]
14. Zhou, T.; Geng, Y.; Ji, C.; Xu, X.; Wang, H.; Pan, J.; Bumberger, J.; Haase, D.; Lausch, A. Prediction of soil organic carbon and
the C:N ratio on a national scale using machine learning and satellite data: A comparison between Sentinel-2, Sentinel-3 and
Landsat-8 images. Sci. Total Environ. 2020, 755, 142661. [CrossRef] [PubMed]
15. Xu, Y.; Li, B.; Shen, X.; Li, K.; Cao, X.; Cui, G.; Yao, Z. Digital soil mapping of soil total nitrogen based on Landsat 8, Sentinel 2,
and WorldView-2 images in smallholder farms in Yellow River Basin, China. Environ. Monit. Assess. 2022, 194, 282. [CrossRef]
[PubMed]
16. Poggio, L.; Gimona, A. Assimilation of optical and radar remote sensing data in 3D mapping of soil properties over large areas.
Sci. Total Environ. 2017, 579, 1094–1110. [CrossRef]
17. Kamran, A.; Younes, G.; Shamsollah, A.; Samaneh, T. Integration of Sentinel-1/2 and topographic attributes to predict the spatial
distribution of soil texture fractions in some agricultural soils of western Iran. Soil Tillage Res. 2023, 229, 105681.
18. Yang, R.; Guo, W. Using time-series Sentinel-1 data for soil prediction on invaded coastal wetlands. Environ. Monit. Assess. 2019,
191, 462. [CrossRef]
19. Zare, S.; Fallah, S.S.R.; Abtahi, S.A. Weakly-coupled geo-statistical mapping of soil salinity to Stepwise Multiple Linear Regression
of MODIS spectral image products. J. Afr. Earth Sci. 2019, 152, 101–114. [CrossRef]
20. Xu, S.; Wang, M.; Shi, X.; Yu, Q.; Zhang, Z. Integrating hyperspectral imaging with machine learning techniques for the
high-resolution mapping of soil nitrogen fractions in soil profiles. Sci. Total Environ. 2021, 754, 142135. [CrossRef]
21. Karunaratne, S.B.; Bishop, T.F.A.; Baldock, J.A.; Odeh, I.O.A. Catchment scale mapping of measureable soil organic carbon
fractions. Geoderma 2014, 219–220, 14–23. [CrossRef]
22. Xu, Y.; Smith, S.E.; Grunwald, S.; Abd-Elrahman, A.; Wani, S.P.; Nair, V.D. Estimating soil total nitrogen in smallholder farm
settings using remote sensing spectral indices and regression kriging. Catena 2018, 163, 111–122. [CrossRef]
23. Westhuizen, S.v.d.; Heuvelink, G.B.M.; Hofmeyr, D.P. Multivariate random forest for digital soil mapping. Geoderma 2023, 431,
116365. [CrossRef]
24. Gomes, L.C.; Faria, R.M.; Souza, E.d.; Veloso, G.V.; Schaefer, C.E.G.R.; Filho, E.I.F. Modelling and mapping soil organic carbon
stocks in Brazil. Geoderma 2019, 340, 337–350. [CrossRef]
25. Wang, S.; Adhikari, K.; Wang, Q.; Jin, X.; Li, H. Role of environmental variables in the spatial distribution of soil carbon (C),
nitrogen (N), and C:N ratio from the northeastern coastal agroecosystems in China. Ecol. Indic. 2018, 84, 263–272. [CrossRef]
26. Zhang, X.; Xue, J.; Chen, S.; Wang, N.; Shi, Z.; Huang, Y.; Zhuo, Z. Digital Mapping of Soil Organic Carbon with Machine Learning
in Dryland of Northeast and North Plain China. Remote Sens. 2022, 14, 2504. [CrossRef]
27. Pham, T.D.; Yokoya, N.; Nguyen, T.T.T.; Le, N.N.; Ha, N.T.; Xia, J.; Takeuchi, W.; Pham, T.D. Improvement of Mangrove Soil
Carbon Stocks Estimation in North Vietnam Using Sentinel-2 Data and Machine Learning Approach. GIScience Remote Sens. 2021,
58, 68–87. [CrossRef]
28. Yang, J.; Fan, J.; Lan, Z.; Mu, X.; Wu, Y.; Xin, Z.; Miping, P.; Zhao, G. Improved Surface Soil Organic Carbon Mapping of
SoilGrids250m Using Sentinel-2 Spectral Images in the Qinghai–Tibetan Plateau. Remote Sens. 2023, 15, 114. [CrossRef]
29. Lan, J.; Hu, N.; Fu, W. Soil carbon–nitrogen coupled accumulation following the natural vegetation restoration of abandoned
farmlands in a karst rocky desertification region. Ecol. Eng. 2020, 158, 106033. [CrossRef]
30. Bhunia, G.S.; Shit, P.K.; Pourghasemi, H.R. Soil organic carbon mapping using remote sensing techniques and multivariate
regression model. Geocarto Int. 2019, 34, 215–226. [CrossRef]
31. John, K.; Isong, I.A.; Kebonye, N.M.; Ayito, E.O.; Agyeman, P.C.; Afu, S.M. Using Machine Learning Algorithms to Estimate
Soil Organic Carbon Variability with Environmental Variables and Soil Nutrient Indicators in an Alluvial Soil. Land 2020, 9, 487.
[CrossRef]
32. Wang, M.; Mao, D.; Xiao, X.; Song, K.; Jia, M.; Ren, C.; Wang, Z. Interannual changes of coastal aquaculture ponds in China at
10-m spatial resolution during 2016–2021. Remote Sens. Environ. 2023, 284, 113347. [CrossRef]
Remote Sens. 2023, 15, 2907 21 of 22

33. Xu, Y.; Wang, X.; Bai, J.; Wang, D.; Wang, W.; Guan, Y. Estimating the spatial distribution of soil total nitrogen and available
potassium in coastal wetland soils in the Yellow River Delta by incorporating multi-source data. Ecol. Indic. 2020, 111, 106002.
[CrossRef]
34. Liu, Y.; Qian, J.; Yue, H. Comprehensive Evaluation of Sentinel-2 Red Edge and Shortwave-Infrared Bands to Estimate Soil
Moisture. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021, 14, 7448–7465. [CrossRef]
35. Nabiollahi, K.; Taghizadeh-Mehrjardi, R.; Shahabi, A.; Heung, B.; Scholten, T. Assessing agricultural salt-affected land using
digital soil mapping and hybridized random forests. Geoderma 2021, 385, 114858. [CrossRef]
36. Taghizadeh-Mehrjardi, R.; Schmidt, K.; Amirian-Chakan, A.; Rentschler, T.; Zeraatpisheh, M.; Sarmadian, F.; Valavi, R.; Davatgar,
N.; Behrens, T.; Scholten, T. Improving the Spatial Prediction of Soil Organic Carbon Content in Two Contrasting Climatic Regions
by Stacking Machine Learning Models and Rescanning Covariate Space. Remote Sens. 2020, 12, 1095. [CrossRef]
37. Bremner, J.M. Determination of nitrogen in soil by the Kjeldahl method. J. Agric. Sci. 1960, 55, 11–33. [CrossRef]
38. Fathololoumi, S.; Vaezi, A.R.; Alavipanah, S.K.; Ghorbani, A.; Biswas, A. Effect of multi-temporal satellite images on soil moisture
prediction using a digital soil mapping approach. Geoderma 2021, 385, 114901. [CrossRef]
39. Song, J.; Gao, J.; Zhang, Y.; Li, F.; Man, W.; Liu, M.; Wang, J.; Li, M.; Zheng, H.; Yang, X.; et al. Estimation of Soil Organic Carbon
Content in Coastal Wetlands with Measured VIS-NIR Spectroscopy Using Optimized Support Vector Machines and Random
Forests. Remote Sens. 2022, 14, 4372. [CrossRef]
40. Hamzehpour, N.; Shafizadeh-Moghadam, H.; Valavi, R. Exploring the driving forces and digital mapping of soil organic carbon
using remote sensing and soil texture. Catena 2019, 182, 104141. [CrossRef]
41. Ridgeway, G. gbm: Generalized boosted regression models. R Package Version 2006, 1, 55.
42. Jia, Y.; Jin, S.; Savi, P.; Gao, Y.; Tang, J.; Chen, Y.; Li, W. GNSS-R Soil Moisture Retrieval Based on a XGboost Machine Learning
Aided Method: Performance and Validation. Remote Sens. 2019, 11, 1655. [CrossRef]
43. Li, Y.; Zeng, H.; Zhang, M.; Wu, B.; Zhao, Y.; Yao, X.; Cheng, T.; Qin, X.; Wu, F. A county-level soybean yield prediction framework
coupled with XGBoost and multidimensional feature engineering. Int. J. Appl. Earth Obs. Geoinf. 2023, 118, 103269. [CrossRef]
44. Kuhn, M.; Johnson, K. Applied Predictive Modeling; Springer: Berlin/Heidelberg, Germany, 2013; Volume 26.
45. Taghizadeh-Mehrjardi, R.; Nabiollahi, K.; Kerry, R. Digital mapping of soil organic carbon at multiple depths using different data
mining techniques in Baneh region, Iran. Geoderma 2016, 266, 98–110. [CrossRef]
46. Aitkenhead, M.J. Mapping peat in Scotland with remote sensing and site characteristics. Eur. J. Soil Sci. 2017, 68, 28–38. [CrossRef]
47. Ottoy, S.; Vos, B.D.; Sindayihebura, A.; Hermy, M.; Orshoven, J.V. Assessing soil organic carbon stocks under current and potential
forest cover using digital soil mapping and spatial generalisation. Ecol. Indic. 2017, 77, 139–150. [CrossRef]
48. Zhang, X.; Yang, C.; Liu, H.; Wu, W. Predictions on organic matter and total nitrogen contents in tobacco-growing soil based on
machine learning. Tob. Sci. Technol. 2022, 55, 20–27. (In Chinese) [CrossRef]
49. Ghosh, S.M.; Behera, M.D.; Jagadish, B.; Das, A.K.; Mishra, D.R. A novel approach for estimation of aboveground biomass of a
carbon-rich mangrove site in India. J. Environ. Manag. 2021, 292, 112816. [CrossRef]
50. Wang, S.; Jin, X.; Adhikari, K.; Li, W.; Yu, M.; Bian, Z.; Wang, Q. Mapping total soil nitrogen from a site in northeastern China.
Catena 2018, 166, 134–146. [CrossRef]
51. Salunke, R.; Nobahar, M.; Alzeghoul, O.E.; Khan, S.; La Cour, I.; Amini, F. Near-Surface Soil Moisture Characterization in
Mississippi’s Highway Slopes Using Machine Learning Methods and UAV-Captured Infrared and Optical Images. Remote Sens.
2023, 15, 1888. [CrossRef]
52. Castaldi, F.; Chabrillat, S.; Don, A.; Wesemael, B.v. Soil Organic Carbon Mapping Using LUCAS Topsoil Database and Sentinel-2
Data: An Approach to Reduce Soil Moisture and Crop Residue Effects. Remote Sens. 2019, 11, 2121. [CrossRef]
53. Zhou, T.; Geng, Y.; Chen, J.; Liu, M.; Haase, D.; Lausch, A. Mapping soil organic carbon content using multi-source remote
sensing variables in the Heihe River Basin in China. Ecol. Indic. 2020, 114, 106288. [CrossRef]
54. Wadoux, A.M.J.-C. Using deep learning for multivariate mapping of soil with quantified uncertainty. Geoderma 2019, 351, 59–70.
[CrossRef]
55. Li, Z.; Liu, F.; Peng, X.; Hu, B.; Song, X. Synergetic use of DEM derivatives, Sentinel-1 and Sentinel-2 data for mapping soil
properties of a sloped cropland based on a two-step ensemble learning method. Sci. Total Environ. 2023, 866, 161421. [CrossRef]
[PubMed]
56. Zhou, Y.; Xue, J.; Chen, S.; Zho, Y.; Liang, Z.; Wang, N.; Shi, Z. Fine-Resolution Mapping of Soil Total Nitrogen across China Based
on Weighted Model Averaging. Remote Sens. 2020, 12, 85. [CrossRef]
57. Yang, R.; Guo, W. Modelling of soil organic carbon and bulk density in invaded coastal wetlands using Sentinel-1 imagery. Int. J.
Appl. Earth Obs. Geoinf. 2019, 82, 101906. [CrossRef]
58. Wang, J.; Bai, J.; Zhao, Q.; Lu, Q.; Xia, Z. Five-year changes in soil organic carbon and total nitrogen in coastal wetlands affected
by flow-sediment regulation in a Chinese delta. Sci. Rep. 2016, 6, 21137. [CrossRef] [PubMed]
59. Guo, Y.; Liu, Y.; Xu, M.; Zhang, X. Modeling and analysis of red edge index estimated by leaf area index in road vagetation. Sci.
Surv. Mapp. 2021, 46, 93–98. [CrossRef]
60. Zhou, T.; Geng, Y.; Chen, J.; Pan, J.; Haase, D.; Lausch, A. High-resolution digital mapping of soil organic carbon and soil total
nitrogen using DEM derivatives, Sentinel-1 and Sentinel-2 data based on machine learning algorithms. Sci. Total Environ. 2020,
729, 138244. [CrossRef] [PubMed]
Remote Sens. 2023, 15, 2907 22 of 22

61. Zhang, H.; Wu, P.; Yin, A.; Yang, X.; Zhang, X.; Zhang, M.; Gao, C. Organic carbon and total nitrogen dynamics of reclaimed soils
following intensive agricultural use in eastern China. Agric. Ecosyst. Environ. 2016, 235, 193–203. [CrossRef]
62. Magalhães, T.M.; Mamugy, F.P.S. Fine root biomass and soil properties following the conversion of miombo woodlands to shifting
cultivation lands. Catena 2020, 194, 104693. [CrossRef]
63. Li, X.; Shang, B.; Wang, D.; Wang, Z.; Wen, X.; Kang, Y. Mapping soil organic carbon and total nitrogen in croplands of the
Corn Belt of Northeast China based on geographically weighted regression kriging model. Comput. Geosci. 2020, 135, 104392.
[CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.